INDEX

Explanations

terms related to medical or biological processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Misspellings and typos

np_acts-logits-general · gemini-2.0-flash

parliament, struggling, certainly, simultaneously

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 समीक्षाओं

-1.03

RenderAtEndOf

-0.91

Архівовано

-0.81

 חיצוניים

-0.78

parsedMessage

-0.74

atisk

-0.72

 nahilalakip

-0.71

MessageOf

-0.71

󠁴

-0.71

chließend

-0.70

POSITIVE LOGITS

<eos>

0.76

<unused63>

0.53

 atitude

0.51

<unused60>

0.50

0.49

тс

0.48

ĺ

0.48

ŕ

0.48

 definately

0.48

<unused61>

0.47

Activations Density 0.437%

terms related to medical or biological processes

Misspellings and typos

parliament, struggling, certainly, simultaneously

No Comments

No Known Activations